activity
20242026
most citedFastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines

2 citations · 3 across the 9 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

DiTango: Cost-Effective Parallel Diffusion Generation with Selective Attention State Reuse

Yuyang Chen, Runxin Zhong, Zan Zong +3

Recent advances in AI-generated content have driven widespread adoption of Diffusion Transformers (DiTs) for high-resolution, long-duration content generation. While parallelizatio…